system

Abstract

The system according to the embodiment aims to understand and explain the operational logic of an AI system. [Solution] A system according to an embodiment includes a collection unit, an analysis unit, a generation unit, and a provision unit. The collection unit collects operational data of an AI system. The analysis unit analyzes the data collected by the collection unit. The generation unit generates an explanation based on the logic analyzed by the analysis unit. The provision unit provides the explanation generated by the generation unit.

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, the operational logic of AI systems was treated as a black box, making it difficult to understand and explain.

[0005] The system according to the embodiment aims to understand and explain the operational logic of an AI system. [Means for solving the problem]

[0006] A system according to an embodiment includes a collection unit, an analysis unit, a generation unit, and a provision unit. The collection unit collects operational data of the AI ​​system. The analysis unit analyzes the data collected by the collection unit. The generation unit generates an explanation based on the logic analyzed by the analysis unit. The provision unit provides the explanation generated by the generation unit. [Effects of the Invention]

[0007] The system according to the embodiment can understand and explain the operational logic of the AI ​​system. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A generative AI system according to an embodiment of the present invention is a system that understands and explains the logic of an AI system to prevent AI from becoming a black box. This generative AI system collects operational data of the AI ​​system, analyzes the collected data, extracts the AI ​​system's logic, and generates a human-understandable explanation based on the extracted logic. This explanation is provided in a user-selectable format, such as text or diagrams. For example, the generative AI system records in detail the input the AI ​​system receives, the processing it performs, and the output it generates. For example, if the AI ​​system performs image recognition, it collects data such as the input image, the processing details, and the recognition results. The generative AI then analyzes the collected data. Based on the collected data, the generative AI analyzes the AI ​​system's logic and identifies the algorithms and models used. For example, it analyzes the layer structure and weight distribution of the neural network. Furthermore, the generative AI generates a human-understandable explanation based on the extracted logic. For example, it explains in text or diagrams the role of each layer of the neural network and the features it extracts. This explanation is provided in a user-selectable format. For example, you can choose from text, diagram, and video formats. This prevents AI systems from becoming black boxes and makes it easier to understand the logic of the AI ​​systems they are implementing. For example, when a company implements an AI system, understanding and explaining its logic can ensure transparency and improve reliability. It can also help AI system developers understand the operation of their systems in detail and identify areas for improvement. This prevents AI systems from becoming black boxes and makes it easier to understand the logic of the AI ​​systems they are implementing.

[0029] A generative AI system according to an embodiment includes a collection unit, an analysis unit, a generation unit, and a provision unit. The collection unit collects operational data of the AI ​​system. For example, the collection unit records in detail what input the AI ​​system received, what processing it performed, and what output it generated. For example, if the AI ​​system performs image recognition, the collection unit collects data such as the input image, processing details, and recognition results. Furthermore, if the AI ​​system performs natural language processing, the collection unit can also collect data such as the input text, processing details, and analysis results. Furthermore, if the AI ​​system uses a predictive model, the collection unit can also collect data such as the input data, processing details, and prediction results. The analysis unit analyzes the data collected by the collection unit. For example, the analysis unit analyzes the logic of the AI ​​system based on the collected data and identifies the algorithm or model used. For example, the analysis unit analyzes the layer structure and weight distribution of a neural network. Furthermore, the analysis unit can analyze the algorithm flow and model structure of the AI ​​system. Furthermore, the analysis unit can analyze resource usage (e.g., CPU and memory usage) during operation of the AI ​​system. The generation unit generates an explanation based on the logic analyzed by the analysis unit. The generation unit, for example, explains in text or diagrams what role each layer of the neural network plays and what features it extracts. The generation unit can also explain in text or diagrams the algorithm flow and model structure of the AI ​​system. Furthermore, the generation unit can also explain in text or diagrams the resource usage status during operation of the AI ​​system. The provision unit provides the explanation generated by the generation unit. The provision unit provides the explanation in, for example, a format selectable by the user. For example, the provision unit provides the explanation in a format such as text, diagram, or video. The provision unit can also estimate the user's emotions and adjust the format of the explanation to be provided based on the estimated user emotions. Furthermore, the provision unit can estimate the user's emotions and adjust the order of the explanations to be provided based on the estimated user emotions.As a result, the generative AI system according to the embodiment can prevent the AI ​​system from becoming a black box, making it easier to understand the logic of the AI ​​system that has been introduced.

[0030] The collection unit can record in detail what input the AI ​​system received, what processing it performed, and what output it generated. For example, when the AI ​​system performs image recognition, the collection unit collects data such as the input image, processing details, and recognition results. For example, when the AI ​​system performs image recognition, the collection unit records the input image in detail, records the processing performed, and records the final recognition result. In addition, when the AI ​​system performs natural language processing, the collection unit can also collect data such as the input text, processing details, and analysis results. For example, when the AI ​​system performs natural language processing, the collection unit records the input text in detail, records the processing performed, and records the final analysis result. Furthermore, when the AI ​​system uses a predictive model, the collection unit can also collect data such as the input data, processing details, and prediction results. For example, when the AI ​​system uses a predictive model, the collection unit records the input data in detail, records the processing performed, and records the final prediction result. This detailed recording of the AI ​​system's operational data improves the accuracy of the analysis. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can collect operational data of the AI ​​system, input the collected data into the generation AI, and have the generation AI analyze the data.

[0031] The analysis unit can analyze the logic of the AI ​​system based on the collected data and identify the algorithms and models used. For example, the analysis unit can analyze the logic of the AI ​​system based on the collected data and identify the algorithms and models used. For example, the analysis unit can analyze the layer structure and weight distribution of a neural network. The analysis unit can also analyze the algorithm flow and model structure of the AI ​​system. Furthermore, the analysis unit can analyze resource usage (e.g., CPU and memory usage) while the AI ​​system is running. For example, the analysis unit can analyze CPU usage while the AI ​​system is running and identify the amount of resources consumed. The analysis unit can also analyze memory usage while the AI ​​system is running and identify the amount of memory used. Furthermore, the analysis unit can analyze disk I / O usage while the AI ​​system is running and identify the amount of disk resources consumed. Identifying the logic of the AI ​​system improves system transparency. Some or all of the above-described processing by the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input collected data into the generation AI and have the generation AI analyze the data.

[0032] The generation unit can use text or diagrams to explain the role of each layer of the neural network and the features it extracts. For example, the generation unit can explain in detail the role of each layer of the neural network and the features it extracts. For example, the generation unit can explain in detail what data the input layer of the neural network receives, what features the intermediate layer extracts, and what results the output layer generates. The generation unit can also use diagrams to illustrate the role of each layer of the neural network in a visually easy-to-understand format. Furthermore, the generation unit can use specific examples to explain the features each layer of the neural network extracts. For example, in image recognition, the generation unit can explain the process in which the input layer receives pixel data of an image, the intermediate layer extracts features such as edges and textures, and the output layer generates a recognition result. This explanation of the role of each layer of the neural network deepens understanding of the system. Some or all of the above-described processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input data from each layer of the neural network into the generation AI and have the generation AI generate text and illustrations that explain the role and characteristics of each layer.

[0033] The providing unit can provide the explanation in a user-selectable format. The providing unit provides the explanation in, for example, a user-selectable format. For example, the providing unit provides the explanation in a format such as text, illustration, or video. The providing unit can also estimate the user's emotions and adjust the format of the explanation to be provided based on the estimated user's emotions. For example, the providing unit can provide a simple text-format explanation when the user is stressed, and a detailed illustration-format explanation when the user is relaxed. The providing unit can also estimate the user's emotions and adjust the order of the explanation to be provided based on the estimated user's emotions. For example, the providing unit can provide the main points first when the user is in a hurry, and provide detailed information in a sequential order when the user is relaxed. This improves user convenience by providing the explanation in a user-selectable format. Some or all of the above-described processing by the providing unit may be performed using, for example, AI, or may be performed without AI. For example, the providing unit can have a generation AI generate explanation formats and select the optimal format based on the user's emotions.

[0034] The providing unit can provide the explanation in a format such as text, diagram, or video. The providing unit can provide the explanation in a format such as text, diagram, or video. For example, if the user selects the text format, the providing unit can provide a detailed text explanation. Furthermore, if the user selects the diagram format, the providing unit can provide a visually easy-to-understand diagram. Furthermore, if the user selects the video format, the providing unit can provide a dynamic explanation. For example, the providing unit can show the operation of the AI ​​system in a video and explain each step in detail. This allows the explanation to be provided in multiple formats, thereby deepening the user's understanding. Some or all of the above-described processing in the providing unit can be performed, for example, using AI or without AI. For example, the providing unit can have a generation AI generate explanation formats and provide the optimal format based on the user's selection.

[0035] The collection unit can record the operating environment of the AI ​​system in detail during collection. The collection unit, for example, records the hardware configuration (CPU, memory, storage, etc.) of the server on which the AI ​​system is running. For example, the collection unit can record in detail the CPU type and clock speed, memory capacity, and storage type and capacity of the server on which the AI ​​system is running. The collection unit can also record version information of the software used by the AI ​​system (operating system, libraries, frameworks, etc.). For example, the collection unit can record in detail the version of the operating system used by the AI ​​system and the versions of the libraries and frameworks used. The collection unit can also record the network environment in which the AI ​​system is running (IP address, network bandwidth, etc.). For example, the collection unit can record in detail the IP address, network bandwidth, network latency, etc. of the network on which the AI ​​system is running. This detailed recording of the operating environment of the AI ​​system improves the accuracy of analysis. Some or all of the above-mentioned processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input operating environment data of the AI ​​system to a generation AI and have the generation AI analyze the data.

[0036] The collection unit can record resource usage during operation of the AI ​​system at the time of collection. The collection unit, for example, records CPU usage in real time while the AI ​​system is operating. For example, the collection unit periodically samples CPU usage while the AI ​​system is operating and records how much resource is being consumed. The collection unit can also record memory usage in real time while the AI ​​system is operating. For example, the collection unit periodically samples memory usage while the AI ​​system is operating and records how much memory is being used. The collection unit can also record disk I / O usage in real time while the AI ​​system is operating. For example, the collection unit periodically samples disk I / O usage while the AI ​​system is operating and records how much disk resource is being consumed. This allows the performance of the AI ​​system to be evaluated by recording resource usage during operation. Some or all of the above-described processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input resource usage data of the AI ​​system to a generation AI and have the generation AI analyze the data.

[0037] During collection, the collection unit can simultaneously collect user operation logs along with the AI ​​system's operation logs. The collection unit, for example, collects user operation logs (clicks, inputs, etc.) while the AI ​​system is operating. For example, the collection unit records the user's click history and input history in detail while the AI ​​system is operating. The collection unit can also collect the user's operation history (page transitions, operation time, etc.) while the AI ​​system is operating. For example, the collection unit records the user's page transition history and operation time in detail while the AI ​​system is operating. Furthermore, the collection unit can also collect user operation errors (input errors, operation errors, etc.) while the AI ​​system is operating. For example, the collection unit records the user's input errors and operation errors in detail while the AI ​​system is operating. By simultaneously collecting the AI ​​system's operation logs and the user's operation logs, the system's operating status can be understood in detail. Some or all of the above-mentioned processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input the AI ​​system's operation logs and the user's operation logs into a generation AI and have the generation AI analyze the data.

[0038] The collection unit can record in detail, at the time of collection, error and warning messages that occur during operation of the AI ​​system. The collection unit, for example, records in detail error messages that occur during operation of the AI ​​system. For example, the collection unit records in detail the content and time of occurrence of error messages that occur during operation of the AI ​​system. The collection unit can also record in detail warning messages that occur during operation of the AI ​​system. For example, the collection unit records in detail the content and time of occurrence of warning messages that occur during operation of the AI ​​system. The collection unit can also record in detail the content of exception handling that occurs during operation of the AI ​​system. For example, the collection unit records in detail the content and time of occurrence of exception handling that occurs during operation of the AI ​​system. This makes it easier to identify problems with the system by recording in detail error and warning messages that occur during operation of the AI ​​system. Some or all of the above-mentioned processing in the collection unit may be performed using AI, for example, or may be performed without using AI. For example, the collection unit can input error and warning messages of the AI ​​system into the generation AI and have the generation AI analyze the data.

[0039] During analysis, the analysis unit can evaluate the performance of the AI ​​system's algorithm. For example, the analysis unit can evaluate the accuracy of the AI ​​system's algorithm and confirm how accurately it operates. For example, the analysis unit can evaluate the accuracy of the AI ​​system's algorithm and confirm the accuracy of prediction results and classification results. The analysis unit can also evaluate the speed of the AI ​​system's algorithm and confirm how long it takes to complete processing. For example, the analysis unit can evaluate the processing speed of the AI ​​system's algorithm and confirm whether it can reduce processing time or provide real-time performance. Furthermore, the analysis unit can evaluate the resource usage efficiency of the AI ​​system's algorithm and confirm how many resources it consumes. For example, the analysis unit can evaluate the resource usage efficiency of the AI ​​system's algorithm and confirm CPU usage and memory usage. This allows the evaluation of the performance of the AI ​​system's algorithm to identify areas for improvement in the system. Some or all of the above-described processing in the analysis unit can be performed using AI, for example, or without AI. For example, the analysis unit can input performance data of the AI ​​system to a generation AI and have the generation AI analyze the data.

[0040] During analysis, the analysis unit can track the change history of the AI ​​system's algorithm and identify which changes have had what impact. The analysis unit, for example, tracks the version history of the AI ​​system's algorithm and records the changes made to each version. For example, the analysis unit may record the version history of the AI ​​system's algorithm in detail and track the changes and modifications made to each version. The analysis unit can also analyze the change history of the AI ​​system's algorithm and identify the impact each change has had on accuracy and speed. For example, the analysis unit may analyze the change history of the AI ​​system's algorithm and identify the impact each change has had on prediction accuracy and processing speed. Furthermore, the analysis unit can identify the optimal version based on the change history of the AI ​​system's algorithm. For example, the analysis unit may identify the version with the highest performance based on the change history of the AI ​​system's algorithm. In this way, the optimal version can be identified by tracking the change history of the AI ​​system's algorithm. Some or all of the above-described processing in the analysis unit may be performed using, or without, AI. For example, the analysis unit may input change history data of the AI ​​system into a generation AI and have the generation AI analyze the data.

[0041] During analysis, the analysis unit can perform a detailed analysis of the parameter settings of the AI ​​system's algorithm. The analysis unit, for example, performs a detailed analysis of the setting values ​​of each parameter of the AI ​​system's algorithm. For example, the analysis unit records the setting values ​​of each parameter of the AI ​​system's algorithm in detail and analyzes the settings. The analysis unit can also analyze the effect of the parameter settings of the AI ​​system's algorithm on accuracy and speed. For example, the analysis unit analyzes the effect of the parameter settings of the AI ​​system's algorithm on prediction accuracy and processing speed. Furthermore, the analysis unit can perform an analysis to optimize the parameter settings of the AI ​​system's algorithm. For example, the analysis unit optimizes the parameter settings of the AI ​​system's algorithm and identifies the settings that provide the highest performance. This enables system optimization by analyzing the parameter settings of the AI ​​system's algorithm in detail. Some or all of the above-described processing in the analysis unit may be performed using, or without, an AI. For example, the analysis unit can input parameter setting data of the AI ​​system to a generation AI and have the generation AI analyze the data.

[0042] During analysis, the analysis unit can analyze the characteristics of the training dataset of the AI ​​system's algorithm. The analysis unit, for example, analyzes the characteristics (such as data distribution and balance) of the training dataset used by the AI ​​system's algorithm. For example, the analysis unit may perform a detailed analysis of the data distribution and balance of the training dataset of the AI ​​system to identify its characteristics. The analysis unit can also analyze the impact of the training dataset of the AI ​​system's algorithm on accuracy and speed. For example, the analysis unit may analyze the impact of the training dataset's characteristics on prediction accuracy and processing speed. Furthermore, the analysis unit can perform analysis to optimize the training dataset of the AI ​​system's algorithm. For example, the analysis unit may optimize the characteristics of the training dataset and identify the dataset with the highest performance. In this way, analyzing the characteristics of the training dataset of the AI ​​system improves the accuracy of the system. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the analysis unit may input characteristic data of the training dataset to the generation AI and cause the generation AI to analyze the data.

[0043] The generation unit can provide a detailed description of each step of the AI ​​system's logic during generation. The generation unit, for example, provides a detailed description of each step (input, processing, and output) of the AI ​​system's logic. For example, the generation unit may record each step of the AI ​​system's logic in detail, explaining what input is received, what processing is performed, and what output is generated. The generation unit may also provide a detailed description of the algorithms and models used in each step of the AI ​​system's logic. For example, the generation unit may record details of the algorithms and models used in each step of the AI ​​system's logic, explaining what algorithms are used and what models are applied. The generation unit may also provide a detailed description of intermediate results generated in each step of the AI ​​system's logic. For example, the generation unit may record intermediate results generated in each step of the AI ​​system's logic, explaining what intermediate results are generated and how they are processed. This detailed description of each step of the AI ​​system's logic deepens understanding of the system. Some or all of the above-described processing in the generation unit may be performed using AI, for example, or may be performed without AI. For example, the generation unit may input logic data of the AI ​​system into a generation AI and cause the generation AI to generate a detailed description of each step.

[0044] The generation unit can compare and explain the advantages and disadvantages of the AI ​​system's logic during generation. For example, the generation unit can provide a detailed explanation of the advantages (accuracy, speed, efficiency, etc.) of the AI ​​system's logic. For example, the generation unit can record the advantages of the AI ​​system's logic and explain what advantages it has. The generation unit can also provide a detailed explanation of the disadvantages (resource consumption, bias, etc.) of the AI ​​system's logic. For example, the generation unit can record the disadvantages of the AI ​​system's logic and explain what problems it has. Furthermore, the generation unit can compare the advantages and disadvantages of the AI ​​system's logic and explain under what circumstances it operates optimally. For example, the generation unit can compare the advantages and disadvantages of the AI ​​system's logic and explain under what conditions it operates most effectively. By comparing and explaining the advantages and disadvantages of the AI ​​system's logic, areas for improvement in the system can be identified. Some or all of the above-described processing in the generation unit can be performed using AI, for example, or without AI. For example, the generation unit can input logic data of the AI ​​system into a generation AI and cause the generation AI to generate a comparative explanation of the advantages and disadvantages.

[0045] The generation unit can provide specific examples of operation of the AI ​​system's logic during generation. For example, when the AI ​​system performs image recognition, the generation unit provides a specific input image and the recognition result. For example, when the AI ​​system performs image recognition, the generation unit provides a specific input image and explains the recognition result for that image in detail. The generation unit can also provide specific input text and its analysis result when the AI ​​system performs natural language processing. For example, when the AI ​​system performs natural language processing, the generation unit provides a specific input text and explains the analysis result for that text in detail. Furthermore, when the AI ​​system uses a predictive model, the generation unit can provide specific input data and its predicted result. For example, when the AI ​​system uses a predictive model, the generation unit provides specific input data and explains the predicted result for that data in detail. This provides specific examples of operation of the AI ​​system's logic, thereby deepening understanding of the system. Some or all of the above-mentioned processing in the generation unit may be performed using AI, for example, or may be performed without AI. For example, the generation unit can input operation example data of the AI ​​system to the generation AI and cause the generation AI to generate specific operation examples.

[0046] The generation unit can suggest improvements to the logic of the AI ​​system during generation. For example, the generation unit suggests improvements to improve the accuracy of the logic of the AI ​​system. For example, the generation unit records specific improvements to improve the accuracy of the logic of the AI ​​system and suggests how to improve the accuracy. The generation unit can also suggest improvements to improve the speed of the logic of the AI ​​system. For example, the generation unit records specific improvements to improve the speed of the logic of the AI ​​system and suggests how to improve the speed. The generation unit can also suggest improvements to improve the resource usage efficiency of the logic of the AI ​​system. For example, the generation unit records specific improvements to improve the resource usage efficiency of the logic of the AI ​​system and suggests how to improve the resource usage efficiency. As a result, by suggesting improvements to the logic of the AI ​​system, the performance of the system is improved. Some or all of the above-mentioned processing in the generation unit may be performed using AI, for example, or may be performed without using AI. For example, the generation unit can input logic data of the AI ​​system to the generation AI and cause the generation AI to generate suggested improvements.

[0047] The providing unit can provide an optimal explanation by referring to the user's past browsing history. The providing unit, for example, provides a related explanation based on content previously viewed by the user. For example, the providing unit references content previously viewed by the user and provides related information preferentially. The providing unit can also provide an optimal explanation based on the user's level of understanding of content previously viewed. For example, the providing unit evaluates the user's level of understanding of content previously viewed and provides an explanation according to the level of understanding. Furthermore, the providing unit can also prioritize providing important information based on the frequency with which the user has previously viewed content. For example, the providing unit prioritizes providing important information based on content frequently viewed by the user in the past. In this way, the optimal explanation can be provided to the user by referring to the user's past browsing history. Some or all of the above-described processing by the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit inputs the user's browsing history data to a generation AI and causes the generation AI to generate an optimal explanation.

[0048] The providing unit can adjust the difficulty of the explanation according to the user's level of expertise when providing the information. For example, if the user is a beginner, the providing unit mainly provides basic information. For example, if the user is a beginner, the providing unit prioritizes explanations of basic concepts and terms. Furthermore, if the user is an intermediate user, the providing unit can provide detailed information to deepen understanding. For example, if the user is an intermediate user, the providing unit provides an explanation including detailed data and graphs to deepen understanding. Furthermore, if the user is an advanced user, the providing unit can provide specialized information to promote a more advanced understanding. For example, if the user is an advanced user, the providing unit explains details of specialized algorithms and models to promote a more advanced understanding. In this way, by adjusting the difficulty of the explanation according to the user's level of expertise, an explanation suitable for the user can be provided. Some or all of the above-mentioned processing by the providing unit may be performed using, for example, AI, or may be performed without AI. For example, the providing unit can input the user's expertise level data into the generation AI and cause the generation AI to adjust the difficulty of the explanation.

[0049] The providing unit can select the optimal display method by taking into consideration the user's device information when providing the display. For example, if the user is using a smartphone, the providing unit provides a display method tailored to the screen size. For example, if the user is using a smartphone, the providing unit provides a layout and font size optimized for the screen size. Furthermore, if the user is using a tablet, the providing unit can also provide a display method optimized for a large screen. For example, if the user is using a tablet, the providing unit provides a layout and detailed information that take advantage of the screen size. Furthermore, if the user is using a desktop, the providing unit can also provide a layout for displaying detailed information. For example, if the user is using a desktop, the providing unit provides a layout for displaying multiple windows and detailed data. This makes it possible to provide the optimal display method by taking into consideration the user's device information. Some or all of the above-described processing by the providing unit may be performed using AI, for example, or may be performed without using AI. For example, the providing unit inputs the user's device information into the generation AI and causes the generation AI to select the optimal display method.

[0050] The providing unit can collect user feedback when providing the explanation and improve the content of the explanation. For example, the providing unit provides an interface through which the user provides feedback on the provided explanation. For example, the providing unit provides a feedback form through which the user can comment on and rate the explanation. The providing unit can also periodically update the content of the explanation based on the user feedback. For example, the providing unit can analyze the user feedback, identify common areas for improvement, and improve the content of the explanation. Furthermore, the providing unit can also personalize the content of the explanation based on the user feedback. For example, the providing unit can provide an optimal explanation for each individual user based on the user feedback. In this way, the content of the explanation can be continuously improved by collecting user feedback. Some or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input user feedback data to a generation AI and cause the generation AI to improve the content of the explanation.

[0051] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0052] The analysis unit can also be equipped with a data anomaly detection function when analyzing the AI ​​system's operational data. For example, the analysis unit can detect abnormal patterns or anomalous values ​​from the collected data and notify the user. The analysis unit can also evaluate the stability of the AI ​​system's operation based on the results of the anomaly detection. Furthermore, the analysis unit can also suggest areas for improvement to the AI ​​system based on the results of the anomaly detection. This can improve the reliability of the AI ​​system's operation.

[0053] The collection unit may also be equipped with a data privacy protection function when collecting operational data of the AI ​​system. For example, the collection unit may anonymize the collected data to protect personal information. The collection unit may also be equipped with a function to obtain user consent when collecting data. Furthermore, the collection unit may also be equipped with a function to notify users of the purpose for which the data will be used after collection. This strengthens data privacy protection and gains user trust.

[0054] The analysis unit can also be equipped with a data visualization function when analyzing the operational data of the AI ​​system. For example, the analysis unit can display the collected data in graphs and charts, making it easier to visually understand trends and patterns in the data. The analysis unit can also evaluate the performance of the AI ​​system based on the data visualization results. Furthermore, the analysis unit can suggest areas for improvement to the AI ​​system based on the data visualization results. This makes it easier to intuitively understand the data analysis results.

[0055] The generation unit may also have an interactive explanation function when explaining the logic of the AI ​​system. For example, when a user inputs a question, the generation unit generates an answer to that question. The generation unit may also have a function that displays a detailed explanation of a specific part when the user clicks on that part. Furthermore, the generation unit may update the content of the explanation in real time based on user feedback. This makes it easier for users to understand the logic of the AI ​​system at their own pace.

[0056] When providing the generated explanation, the providing unit can select an explanation format according to the user's learning style. For example, the providing unit can provide an illustrated explanation to a user who prefers visual learning, and an audio explanation to a user who prefers auditory learning. The providing unit can also provide an interactive simulation to a user who prefers hands-on learning. Furthermore, the providing unit can adjust the difficulty of the explanation according to the user's learning progress. This can maximize the user's learning effect.

[0057] The processing flow of the first embodiment will be briefly explained below.

[0058] Step 1: The collection unit collects operational data of the AI ​​system. For example, the collection unit records in detail what input the AI ​​system received, what processing it performed, and what output it generated. Specifically, in the case of image recognition, data such as the input image, processing details, and recognition results are collected. In the case of natural language processing, data such as the input text, processing details, and analysis results are collected. Furthermore, when a predictive model is used, data such as the input data, processing details, and prediction results are collected. Step 2: The analysis unit analyzes the data collected by the collection unit. Based on the collected data, the analysis unit analyzes the logic of the AI ​​system and identifies the algorithms and models used. Specifically, it analyzes the layer structure and weight distribution of the neural network, the algorithm flow and model structure, and resource usage during operation (e.g., CPU and memory usage). Step 3: The generator generates an explanation based on the logic analyzed by the analyzer. The generator uses text and diagrams to explain the role of each layer of the neural network, feature extraction, algorithm flow, model structure, and resource usage during operation. Step 4: The providing unit provides the explanation generated by the generating unit. The providing unit provides the explanation in a format selectable by the user (e.g., text format, diagram format, video format, etc.). The providing unit can also estimate the user's emotions and adjust the format and order of the explanation based on the estimated emotions.

[0059] (Example 2) A generative AI system according to an embodiment of the present invention is a system that understands and explains the logic of an AI system to prevent AI from becoming a black box. This generative AI system collects operational data of the AI ​​system, analyzes the collected data, extracts the AI ​​system's logic, and generates a human-understandable explanation based on the extracted logic. This explanation is provided in a user-selectable format, such as text or diagrams. For example, the generative AI system records in detail the input the AI ​​system receives, the processing it performs, and the output it generates. For example, if the AI ​​system performs image recognition, it collects data such as the input image, the processing details, and the recognition results. The generative AI then analyzes the collected data. Based on the collected data, the generative AI analyzes the AI ​​system's logic and identifies the algorithms and models used. For example, it analyzes the layer structure and weight distribution of the neural network. Furthermore, the generative AI generates a human-understandable explanation based on the extracted logic. For example, it explains in text or diagrams the role of each layer of the neural network and the features it extracts. This explanation is provided in a user-selectable format. For example, you can choose from text, diagram, and video formats. This prevents AI systems from becoming black boxes and makes it easier to understand the logic of the AI ​​systems they are implementing. For example, when a company implements an AI system, understanding and explaining its logic can ensure transparency and improve reliability. It can also help AI system developers understand the operation of their systems in detail and identify areas for improvement. This prevents AI systems from becoming black boxes and makes it easier to understand the logic of the AI ​​systems they are implementing.

[0060] A generative AI system according to an embodiment includes a collection unit, an analysis unit, a generation unit, and a provision unit. The collection unit collects operational data of the AI ​​system. For example, the collection unit records in detail what input the AI ​​system received, what processing it performed, and what output it generated. For example, if the AI ​​system performs image recognition, the collection unit collects data such as the input image, processing details, and recognition results. Furthermore, if the AI ​​system performs natural language processing, the collection unit can also collect data such as the input text, processing details, and analysis results. Furthermore, if the AI ​​system uses a predictive model, the collection unit can also collect data such as the input data, processing details, and prediction results. The analysis unit analyzes the data collected by the collection unit. For example, the analysis unit analyzes the logic of the AI ​​system based on the collected data and identifies the algorithm or model used. For example, the analysis unit analyzes the layer structure and weight distribution of a neural network. Furthermore, the analysis unit can analyze the algorithm flow and model structure of the AI ​​system. Furthermore, the analysis unit can analyze resource usage (e.g., CPU and memory usage) during operation of the AI ​​system. The generation unit generates an explanation based on the logic analyzed by the analysis unit. The generation unit, for example, explains in text or diagrams what role each layer of the neural network plays and what features it extracts. The generation unit can also explain in text or diagrams the algorithm flow and model structure of the AI ​​system. Furthermore, the generation unit can also explain in text or diagrams the resource usage status during operation of the AI ​​system. The provision unit provides the explanation generated by the generation unit. The provision unit provides the explanation in, for example, a format selectable by the user. For example, the provision unit provides the explanation in a format such as text, diagram, or video. The provision unit can also estimate the user's emotions and adjust the format of the explanation to be provided based on the estimated user emotions. Furthermore, the provision unit can estimate the user's emotions and adjust the order of the explanations to be provided based on the estimated user emotions.As a result, the generative AI system according to the embodiment can prevent the AI ​​system from becoming a black box, making it easier to understand the logic of the AI ​​system that has been introduced.

[0061] The collection unit can record in detail what input the AI ​​system received, what processing it performed, and what output it generated. For example, when the AI ​​system performs image recognition, the collection unit collects data such as the input image, processing details, and recognition results. For example, when the AI ​​system performs image recognition, the collection unit records the input image in detail, records the processing performed, and records the final recognition result. In addition, when the AI ​​system performs natural language processing, the collection unit can also collect data such as the input text, processing details, and analysis results. For example, when the AI ​​system performs natural language processing, the collection unit records the input text in detail, records the processing performed, and records the final analysis result. Furthermore, when the AI ​​system uses a predictive model, the collection unit can also collect data such as the input data, processing details, and prediction results. For example, when the AI ​​system uses a predictive model, the collection unit records the input data in detail, records the processing performed, and records the final prediction result. This detailed recording of the AI ​​system's operational data improves the accuracy of the analysis. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can collect operational data of the AI ​​system, input the collected data into the generation AI, and have the generation AI analyze the data.

[0062] The analysis unit can analyze the logic of the AI ​​system based on the collected data and identify the algorithms and models used. For example, the analysis unit can analyze the logic of the AI ​​system based on the collected data and identify the algorithms and models used. For example, the analysis unit can analyze the layer structure and weight distribution of a neural network. The analysis unit can also analyze the algorithm flow and model structure of the AI ​​system. Furthermore, the analysis unit can analyze resource usage (e.g., CPU and memory usage) while the AI ​​system is running. For example, the analysis unit can analyze CPU usage while the AI ​​system is running and identify the amount of resources consumed. The analysis unit can also analyze memory usage while the AI ​​system is running and identify the amount of memory used. Furthermore, the analysis unit can analyze disk I / O usage while the AI ​​system is running and identify the amount of disk resources consumed. Identifying the logic of the AI ​​system improves system transparency. Some or all of the above-described processing by the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input collected data into the generation AI and have the generation AI analyze the data.

[0063] The generation unit can use text or diagrams to explain the role of each layer of the neural network and the features it extracts. For example, the generation unit can explain in detail the role of each layer of the neural network and the features it extracts. For example, the generation unit can explain in detail what data the input layer of the neural network receives, what features the intermediate layer extracts, and what results the output layer generates. The generation unit can also use diagrams to illustrate the role of each layer of the neural network in a visually easy-to-understand format. Furthermore, the generation unit can use specific examples to explain the features each layer of the neural network extracts. For example, in image recognition, the generation unit can explain the process in which the input layer receives pixel data of an image, the intermediate layer extracts features such as edges and textures, and the output layer generates a recognition result. This explanation of the role of each layer of the neural network deepens understanding of the system. Some or all of the above-described processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input data from each layer of the neural network into the generation AI and have the generation AI generate text and illustrations that explain the role and characteristics of each layer.

[0064] The providing unit can provide the explanation in a user-selectable format. The providing unit provides the explanation in, for example, a user-selectable format. For example, the providing unit provides the explanation in a format such as text, illustration, or video. The providing unit can also estimate the user's emotions and adjust the format of the explanation to be provided based on the estimated user's emotions. For example, the providing unit can provide a simple text-format explanation when the user is stressed, and a detailed illustration-format explanation when the user is relaxed. The providing unit can also estimate the user's emotions and adjust the order of the explanation to be provided based on the estimated user's emotions. For example, the providing unit can provide the main points first when the user is in a hurry, and provide detailed information in a sequential order when the user is relaxed. This improves user convenience by providing the explanation in a user-selectable format. Some or all of the above-described processing by the providing unit may be performed using, for example, AI, or may be performed without AI. For example, the providing unit can have a generation AI generate explanation formats and select the optimal format based on the user's emotions.

[0065] The providing unit can provide the explanation in a format such as text, diagram, or video. The providing unit can provide the explanation in a format such as text, diagram, or video. For example, if the user selects the text format, the providing unit can provide a detailed text explanation. Furthermore, if the user selects the diagram format, the providing unit can provide a visually easy-to-understand diagram. Furthermore, if the user selects the video format, the providing unit can provide a dynamic explanation. For example, the providing unit can show the operation of the AI ​​system in a video and explain each step in detail. This allows the explanation to be provided in multiple formats, thereby deepening the user's understanding. Some or all of the above-described processing in the providing unit can be performed, for example, using AI or without AI. For example, the providing unit can have a generation AI generate explanation formats and provide the optimal format based on the user's selection.

[0066] The collection unit can estimate the user's emotions and adjust the type of data to be collected based on the estimated user emotions. For example, when the user is feeling stressed, the collection unit limits the type of data to be collected and collects only the minimum necessary data. For example, when the user is feeling stressed, the collection unit collects only important data and refrains from collecting detailed data. The collection unit can also collect detailed data and obtain more information when the user is relaxed. For example, when the user is relaxed, the collection unit collects detailed log data and sensor data. Furthermore, when the user is in a hurry, the collection unit can narrow the type of data to be collected and complete collection quickly. For example, when the user is in a hurry, the collection unit prioritizes collecting the minimum necessary data and shortens the collection time. This improves the quality of the collected data by adjusting the type of data to be collected according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit may input user emotion data into the generation AI and have the generation AI adjust the type of data.

[0067] The collection unit can record the operating environment of the AI ​​system in detail during collection. The collection unit, for example, records the hardware configuration (CPU, memory, storage, etc.) of the server on which the AI ​​system is running. For example, the collection unit can record in detail the CPU type and clock speed, memory capacity, and storage type and capacity of the server on which the AI ​​system is running. The collection unit can also record version information of the software used by the AI ​​system (operating system, libraries, frameworks, etc.). For example, the collection unit can record in detail the version of the operating system used by the AI ​​system and the versions of the libraries and frameworks used. The collection unit can also record the network environment in which the AI ​​system is running (IP address, network bandwidth, etc.). For example, the collection unit can record in detail the IP address, network bandwidth, network latency, etc. of the network on which the AI ​​system is running. This detailed recording of the operating environment of the AI ​​system improves the accuracy of analysis. Some or all of the above-mentioned processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input operating environment data of the AI ​​system to a generation AI and have the generation AI analyze the data.

[0068] The collection unit can record resource usage during operation of the AI ​​system at the time of collection. The collection unit, for example, records CPU usage in real time while the AI ​​system is operating. For example, the collection unit periodically samples CPU usage while the AI ​​system is operating and records how much resource is being consumed. The collection unit can also record memory usage in real time while the AI ​​system is operating. For example, the collection unit periodically samples memory usage while the AI ​​system is operating and records how much memory is being used. The collection unit can also record disk I / O usage in real time while the AI ​​system is operating. For example, the collection unit periodically samples disk I / O usage while the AI ​​system is operating and records how much disk resource is being consumed. This allows the performance of the AI ​​system to be evaluated by recording resource usage during operation. Some or all of the above-described processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input resource usage data of the AI ​​system to a generation AI and have the generation AI analyze the data.

[0069] The collection unit can estimate the user's emotions and determine the priority of data to be collected based on the estimated user emotions. For example, when the user is stressed, the collection unit prioritizes collecting important data. For example, when the user is stressed, the collection unit prioritizes collecting important data and refrains from collecting detailed data. The collection unit can also prioritize collecting detailed data when the user is relaxed. For example, when the user is relaxed, the collection unit prioritizes collecting detailed log data and sensor data. Furthermore, when the user is in a hurry, the collection unit can prioritize shortening the collection time and prioritize collecting the minimum necessary data. For example, when the user is in a hurry, the collection unit prioritizes collecting the minimum necessary data and shortens the collection time. In this way, by determining the priority of data to be collected according to the user's emotions, important data can be collected preferentially. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit may input user emotion data into the generation AI and have the generation AI determine the priority of the data.

[0070] During collection, the collection unit can simultaneously collect user operation logs along with the AI ​​system's operation logs. The collection unit, for example, collects user operation logs (clicks, inputs, etc.) while the AI ​​system is operating. For example, the collection unit records the user's click history and input history in detail while the AI ​​system is operating. The collection unit can also collect the user's operation history (page transitions, operation time, etc.) while the AI ​​system is operating. For example, the collection unit records the user's page transition history and operation time in detail while the AI ​​system is operating. Furthermore, the collection unit can also collect user operation errors (input errors, operation errors, etc.) while the AI ​​system is operating. For example, the collection unit records the user's input errors and operation errors in detail while the AI ​​system is operating. By simultaneously collecting the AI ​​system's operation logs and the user's operation logs, the system's operating status can be understood in detail. Some or all of the above-mentioned processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input the AI ​​system's operation logs and the user's operation logs into a generation AI and have the generation AI analyze the data.

[0071] The collection unit can record in detail, at the time of collection, error and warning messages that occur during operation of the AI ​​system. The collection unit, for example, records in detail error messages that occur during operation of the AI ​​system. For example, the collection unit records in detail the content and time of occurrence of error messages that occur during operation of the AI ​​system. The collection unit can also record in detail warning messages that occur during operation of the AI ​​system. For example, the collection unit records in detail the content and time of occurrence of warning messages that occur during operation of the AI ​​system. The collection unit can also record in detail the content of exception handling that occurs during operation of the AI ​​system. For example, the collection unit records in detail the content and time of occurrence of exception handling that occurs during operation of the AI ​​system. This makes it easier to identify problems with the system by recording in detail error and warning messages that occur during operation of the AI ​​system. Some or all of the above-mentioned processing in the collection unit may be performed using AI, for example, or may be performed without using AI. For example, the collection unit can input error and warning messages of the AI ​​system into the generation AI and have the generation AI analyze the data.

[0072] The analysis unit can estimate the user's emotions and adjust the depth of the analysis based on the estimated user emotions. For example, if the user is feeling stressed, the analysis unit can reduce the depth of the analysis and provide concise analysis results. For example, if the user is feeling stressed, the analysis unit can analyze only important points and refrain from detailed analysis. Furthermore, if the user is relaxed, the analysis unit can increase the depth of the analysis and provide detailed analysis results. For example, if the user is relaxed, the analysis unit can perform detailed data analysis and provide comprehensive analysis results. Furthermore, if the user is in a hurry, the analysis unit can reduce the depth of the analysis and provide analysis results quickly. For example, if the user is in a hurry, the analysis unit can analyze the minimum necessary data and provide results quickly. This allows the analysis results to be tailored to the user by adjusting the depth of the analysis according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input user emotion data to the generation AI and have the generation AI adjust the depth of analysis.

[0073] During analysis, the analysis unit can evaluate the performance of the AI ​​system's algorithm. For example, the analysis unit can evaluate the accuracy of the AI ​​system's algorithm and confirm how accurately it operates. For example, the analysis unit can evaluate the accuracy of the AI ​​system's algorithm and confirm the accuracy of prediction results and classification results. The analysis unit can also evaluate the speed of the AI ​​system's algorithm and confirm how long it takes to complete processing. For example, the analysis unit can evaluate the processing speed of the AI ​​system's algorithm and confirm whether it can reduce processing time or provide real-time performance. Furthermore, the analysis unit can evaluate the resource usage efficiency of the AI ​​system's algorithm and confirm how many resources it consumes. For example, the analysis unit can evaluate the resource usage efficiency of the AI ​​system's algorithm and confirm CPU usage and memory usage. This allows the evaluation of the performance of the AI ​​system's algorithm to identify areas for improvement in the system. Some or all of the above-described processing in the analysis unit can be performed using AI, for example, or without AI. For example, the analysis unit can input performance data of the AI ​​system to a generation AI and have the generation AI analyze the data.

[0074] During analysis, the analysis unit can track the change history of the AI ​​system's algorithm and identify which changes have had what impact. The analysis unit, for example, tracks the version history of the AI ​​system's algorithm and records the changes made to each version. For example, the analysis unit may record the version history of the AI ​​system's algorithm in detail and track the changes and modifications made to each version. The analysis unit can also analyze the change history of the AI ​​system's algorithm and identify the impact each change has had on accuracy and speed. For example, the analysis unit may analyze the change history of the AI ​​system's algorithm and identify the impact each change has had on prediction accuracy and processing speed. Furthermore, the analysis unit can identify the optimal version based on the change history of the AI ​​system's algorithm. For example, the analysis unit may identify the version with the highest performance based on the change history of the AI ​​system's algorithm. In this way, the optimal version can be identified by tracking the change history of the AI ​​system's algorithm. Some or all of the above-described processing in the analysis unit may be performed using, or without, AI. For example, the analysis unit may input change history data of the AI ​​system into a generation AI and have the generation AI analyze the data.

[0075] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, when the user is stressed, the analysis unit provides a simple, highly visible display method. For example, when the user is stressed, the analysis unit emphasizes only important points and refrains from providing detailed information. Furthermore, when the user is relaxed, the analysis unit can provide a display method that includes detailed information. For example, when the user is relaxed, the analysis unit provides a display method that includes detailed data and graphs. Furthermore, when the user is in a hurry, the analysis unit can provide a display method that focuses on the main points. For example, when the user is in a hurry, the analysis unit prioritizes displaying the minimum necessary information and quickly provides results. This allows the display method of the analysis results to be adjusted according to the user's emotions, thereby providing a display method that is suitable for the user. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit can be performed using, for example, an AI, or without an AI. For example, the analysis unit can input the user's emotional data into the generation AI and have the generation AI adjust the display method.

[0076] During analysis, the analysis unit can perform a detailed analysis of the parameter settings of the AI ​​system's algorithm. The analysis unit, for example, performs a detailed analysis of the setting values ​​of each parameter of the AI ​​system's algorithm. For example, the analysis unit records the setting values ​​of each parameter of the AI ​​system's algorithm in detail and analyzes the settings. The analysis unit can also analyze the effect of the parameter settings of the AI ​​system's algorithm on accuracy and speed. For example, the analysis unit analyzes the effect of the parameter settings of the AI ​​system's algorithm on prediction accuracy and processing speed. Furthermore, the analysis unit can perform an analysis to optimize the parameter settings of the AI ​​system's algorithm. For example, the analysis unit optimizes the parameter settings of the AI ​​system's algorithm and identifies the settings that provide the highest performance. This enables system optimization by analyzing the parameter settings of the AI ​​system's algorithm in detail. Some or all of the above-described processing in the analysis unit may be performed using, or without, an AI. For example, the analysis unit can input parameter setting data of the AI ​​system to a generation AI and have the generation AI analyze the data.

[0077] During analysis, the analysis unit can analyze the characteristics of the training dataset of the AI ​​system's algorithm. The analysis unit, for example, analyzes the characteristics (such as data distribution and balance) of the training dataset used by the AI ​​system's algorithm. For example, the analysis unit may perform a detailed analysis of the data distribution and balance of the training dataset of the AI ​​system to identify its characteristics. The analysis unit can also analyze the impact of the training dataset of the AI ​​system's algorithm on accuracy and speed. For example, the analysis unit may analyze the impact of the training dataset's characteristics on prediction accuracy and processing speed. Furthermore, the analysis unit can perform analysis to optimize the training dataset of the AI ​​system's algorithm. For example, the analysis unit may optimize the characteristics of the training dataset and identify the dataset with the highest performance. In this way, analyzing the characteristics of the training dataset of the AI ​​system improves the accuracy of the system. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the analysis unit may input characteristic data of the training dataset to the generation AI and cause the generation AI to analyze the data.

[0078] The generation unit can estimate the user's emotions and adjust the level of detail of the generated explanation based on the estimated user emotions. For example, when the user is stressed, the generation unit generates a concise and to-the-point explanation. For example, when the user is stressed, the generation unit emphasizes only the important points and refrains from detailed explanations. The generation unit can also generate an explanation including detailed information when the user is relaxed. For example, when the user is relaxed, the generation unit generates an explanation including detailed data and graphs. Furthermore, when the user is in a hurry, the generation unit can generate a short and to-the-point explanation. For example, when the user is in a hurry, the generation unit prioritizes providing the minimum necessary information and provides results quickly. This allows the user to be provided with an explanation that is appropriate for the user by adjusting the level of detail of the explanation according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit can be performed using, for example, AI, or without AI. For example, the generation unit can input the user's emotional data into the generation AI and have the generation AI adjust the level of detail of the explanation.

[0079] The generation unit can provide a detailed description of each step of the AI ​​system's logic during generation. The generation unit, for example, provides a detailed description of each step (input, processing, and output) of the AI ​​system's logic. For example, the generation unit may record each step of the AI ​​system's logic in detail, explaining what input is received, what processing is performed, and what output is generated. The generation unit may also provide a detailed description of the algorithms and models used in each step of the AI ​​system's logic. For example, the generation unit may record details of the algorithms and models used in each step of the AI ​​system's logic, explaining what algorithms are used and what models are applied. The generation unit may also provide a detailed description of intermediate results generated in each step of the AI ​​system's logic. For example, the generation unit may record intermediate results generated in each step of the AI ​​system's logic, explaining what intermediate results are generated and how they are processed. This detailed description of each step of the AI ​​system's logic deepens understanding of the system. Some or all of the above-described processing in the generation unit may be performed using AI, for example, or may be performed without AI. For example, the generation unit may input logic data of the AI ​​system into a generation AI and cause the generation AI to generate a detailed description of each step.

[0080] The generation unit can compare and explain the advantages and disadvantages of the AI ​​system's logic during generation. For example, the generation unit can provide a detailed explanation of the advantages (accuracy, speed, efficiency, etc.) of the AI ​​system's logic. For example, the generation unit can record the advantages of the AI ​​system's logic and explain what advantages it has. The generation unit can also provide a detailed explanation of the disadvantages (resource consumption, bias, etc.) of the AI ​​system's logic. For example, the generation unit can record the disadvantages of the AI ​​system's logic and explain what problems it has. Furthermore, the generation unit can compare the advantages and disadvantages of the AI ​​system's logic and explain under what circumstances it operates optimally. For example, the generation unit can compare the advantages and disadvantages of the AI ​​system's logic and explain under what conditions it operates most effectively. By comparing and explaining the advantages and disadvantages of the AI ​​system's logic, areas for improvement in the system can be identified. Some or all of the above-described processing in the generation unit can be performed using AI, for example, or without AI. For example, the generation unit can input logic data of the AI ​​system into a generation AI and cause the generation AI to generate a comparative explanation of the advantages and disadvantages.

[0081] The generation unit can estimate the user's emotions and adjust the format of the generated explanation based on the estimated user's emotions. For example, if the user is stressed, the generation unit generates a simple text-format explanation. For example, if the user is stressed, the generation unit emphasizes only the important points and refrains from detailed explanations. The generation unit can also generate a detailed illustrated explanation if the user is relaxed. For example, if the user is relaxed, the generation unit generates an illustrated explanation including detailed data and graphs. Furthermore, if the user is in a hurry, the generation unit can generate a short video-format explanation. For example, if the user is in a hurry, the generation unit prioritizes providing the minimum necessary information and quickly provides results. This allows the explanation to be provided in a format suitable for the user by adjusting the format of the explanation according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the generation unit can be performed using, for example, AI, or without AI. For example, the generation unit can input the user's emotional data into the generation AI and have the generation AI adjust the format of the explanation.

[0082] The generation unit can provide specific examples of operation of the AI ​​system's logic during generation. For example, when the AI ​​system performs image recognition, the generation unit provides a specific input image and the recognition result. For example, when the AI ​​system performs image recognition, the generation unit provides a specific input image and explains the recognition result for that image in detail. The generation unit can also provide specific input text and its analysis result when the AI ​​system performs natural language processing. For example, when the AI ​​system performs natural language processing, the generation unit provides a specific input text and explains the analysis result for that text in detail. Furthermore, when the AI ​​system uses a predictive model, the generation unit can provide specific input data and its predicted result. For example, when the AI ​​system uses a predictive model, the generation unit provides specific input data and explains the predicted result for that data in detail. This provides specific examples of operation of the AI ​​system's logic, thereby deepening understanding of the system. Some or all of the above-mentioned processing in the generation unit may be performed using AI, for example, or may be performed without AI. For example, the generation unit can input operation example data of the AI ​​system to the generation AI and cause the generation AI to generate specific operation examples.

[0083] The generation unit can suggest improvements to the logic of the AI ​​system during generation. For example, the generation unit suggests improvements to improve the accuracy of the logic of the AI ​​system. For example, the generation unit records specific improvements to improve the accuracy of the logic of the AI ​​system and suggests how to improve the accuracy. The generation unit can also suggest improvements to improve the speed of the logic of the AI ​​system. For example, the generation unit records specific improvements to improve the speed of the logic of the AI ​​system and suggests how to improve the speed. The generation unit can also suggest improvements to improve the resource usage efficiency of the logic of the AI ​​system. For example, the generation unit records specific improvements to improve the resource usage efficiency of the logic of the AI ​​system and suggests how to improve the resource usage efficiency. As a result, by suggesting improvements to the logic of the AI ​​system, the performance of the system is improved. Some or all of the above-mentioned processing in the generation unit may be performed using AI, for example, or may be performed without using AI. For example, the generation unit can input logic data of the AI ​​system to the generation AI and cause the generation AI to generate suggested improvements.

[0084] The providing unit can estimate the user's emotions and adjust the order of explanations to be provided based on the estimated user emotions. For example, if the user is feeling stressed, the providing unit provides important information first. For example, if the user is feeling stressed, the providing unit prioritizes explaining important points and postpones detailed information. The providing unit can also provide detailed information in an orderly manner if the user is relaxed. For example, if the user is relaxed, the providing unit provides an explanation including detailed data and graphs in an orderly manner. Furthermore, if the user is in a hurry, the providing unit can provide the main points first. For example, if the user is in a hurry, the providing unit prioritizes providing the minimum necessary information and quickly provides results. This allows the explanations to be provided in an order appropriate for the user by adjusting the order of explanations according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the providing unit can be performed, for example, using AI or without AI. For example, the providing unit can input the user's emotional data into the generating AI and have the generating AI adjust the order of explanations.

[0085] The providing unit can provide an optimal explanation by referring to the user's past browsing history. The providing unit, for example, provides a related explanation based on content previously viewed by the user. For example, the providing unit references content previously viewed by the user and provides related information preferentially. The providing unit can also provide an optimal explanation based on the user's level of understanding of content previously viewed. For example, the providing unit evaluates the user's level of understanding of content previously viewed and provides an explanation according to the level of understanding. Furthermore, the providing unit can also prioritize providing important information based on the frequency with which the user has previously viewed content. For example, the providing unit prioritizes providing important information based on content frequently viewed by the user in the past. In this way, the optimal explanation can be provided to the user by referring to the user's past browsing history. Some or all of the above-described processing by the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit inputs the user's browsing history data to a generation AI and causes the generation AI to generate an optimal explanation.

[0086] The providing unit can adjust the difficulty of the explanation according to the user's level of expertise when providing the information. For example, if the user is a beginner, the providing unit mainly provides basic information. For example, if the user is a beginner, the providing unit prioritizes explanations of basic concepts and terms. Furthermore, if the user is an intermediate user, the providing unit can provide detailed information to deepen understanding. For example, if the user is an intermediate user, the providing unit provides an explanation including detailed data and graphs to deepen understanding. Furthermore, if the user is an advanced user, the providing unit can provide specialized information to promote a more advanced understanding. For example, if the user is an advanced user, the providing unit explains details of specialized algorithms and models to promote a more advanced understanding. In this way, by adjusting the difficulty of the explanation according to the user's level of expertise, an explanation suitable for the user can be provided. Some or all of the above-mentioned processing by the providing unit may be performed using, for example, AI, or may be performed without AI. For example, the providing unit can input the user's expertise level data into the generation AI and cause the generation AI to adjust the difficulty of the explanation.

[0087] The providing unit can estimate the user's emotions and adjust the frequency of explanations provided based on the estimated user emotions. For example, when the user is feeling stressed, the providing unit reduces the frequency of explanations and provides the minimum necessary information. For example, when the user is feeling stressed, the providing unit emphasizes only the important points and refrains from providing detailed information. The providing unit can also increase the frequency of explanations and provide detailed information when the user is relaxed. For example, when the user is relaxed, the providing unit frequently provides explanations including detailed data and graphs. Furthermore, when the user is in a hurry, the providing unit can reduce the frequency of explanations and provide information that focuses on the main points. For example, when the user is in a hurry, the providing unit prioritizes providing the minimum necessary information and provides results quickly. In this way, by adjusting the frequency of explanations according to the user's emotions, explanations can be provided at a frequency appropriate for the user. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit may input user emotion data to the generating AI and cause the generating AI to adjust the frequency of explanations.

[0088] The providing unit can select the optimal display method by taking into consideration the user's device information when providing the display. For example, if the user is using a smartphone, the providing unit provides a display method tailored to the screen size. For example, if the user is using a smartphone, the providing unit provides a layout and font size optimized for the screen size. Furthermore, if the user is using a tablet, the providing unit can also provide a display method optimized for a large screen. For example, if the user is using a tablet, the providing unit provides a layout and detailed information that take advantage of the screen size. Furthermore, if the user is using a desktop, the providing unit can also provide a layout for displaying detailed information. For example, if the user is using a desktop, the providing unit provides a layout for displaying multiple windows and detailed data. This makes it possible to provide the optimal display method by taking into consideration the user's device information. Some or all of the above-described processing by the providing unit may be performed using AI, for example, or may be performed without using AI. For example, the providing unit inputs the user's device information into the generation AI and causes the generation AI to select the optimal display method.

[0089] The providing unit can collect user feedback when providing the explanation and improve the content of the explanation. For example, the providing unit provides an interface through which the user provides feedback on the provided explanation. For example, the providing unit provides a feedback form through which the user can comment on and rate the explanation. The providing unit can also periodically update the content of the explanation based on the user feedback. For example, the providing unit can analyze the user feedback, identify common areas for improvement, and improve the content of the explanation. Furthermore, the providing unit can also personalize the content of the explanation based on the user feedback. For example, the providing unit can provide an optimal explanation for each individual user based on the user feedback. In this way, the content of the explanation can be continuously improved by collecting user feedback. Some or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input user feedback data to a generation AI and cause the generation AI to improve the content of the explanation. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, analysis unit, generation unit, and provision unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects operational data of the AI ​​system using the camera 42 and microphone 38B of the smart device 14 and records the data in detail using the control unit 46A. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the logic of the AI ​​system based on the collected data. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates an explanation based on the analyzed logic. The provision unit is realized, for example, by the control unit 46A of the smart device 14 and provides the generated explanation in a format selectable by the user. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, analysis unit, generation unit, and provision unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects operational data of the AI ​​system using the camera 42 and microphone 238 of the smart glasses 214 and records the data in detail using the control unit 46A. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the logic of the AI ​​system based on the collected data. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates an explanation based on the analyzed logic. The provision unit is realized, for example, by the control unit 46A of the smart glasses 214 and provides the generated explanation in a format selectable by the user. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned collection unit, analysis unit, generation unit, and provision unit is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the collection unit collects operational data of the AI ​​system using the camera 42 and microphone 238 of the headset-type terminal 314 and records the data in detail using the control unit 46A. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the logic of the AI ​​system based on the collected data. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates an explanation based on the analyzed logic. The provision unit is realized, for example, by the control unit 46A of the headset-type terminal 314 and provides the generated explanation in a format selectable by the user. === Hard Collateral 1-4 === Each of the multiple elements including the collection unit, analysis unit, generation unit, and provision unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects operation data of the AI ​​system using the camera 42 and microphone 238 of the robot 414 and records the data in detail using the control unit 46A. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the logic of the AI ​​system based on the collected data. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates an explanation based on the analyzed logic. The provision unit is realized, for example, by the control unit 46A of the robot 414 and provides the generated explanation in a format selectable by the user.

[0090] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0091] The analysis unit can also be equipped with a data anomaly detection function when analyzing the AI ​​system's operational data. For example, the analysis unit can detect abnormal patterns or anomalous values ​​from the collected data and notify the user. The analysis unit can also evaluate the stability of the AI ​​system's operation based on the results of the anomaly detection. Furthermore, the analysis unit can also suggest areas for improvement to the AI ​​system based on the results of the anomaly detection. This can improve the reliability of the AI ​​system's operation.

[0092] The collection unit may also be equipped with a data privacy protection function when collecting operational data of the AI ​​system. For example, the collection unit may anonymize the collected data to protect personal information. The collection unit may also be equipped with a function to obtain user consent when collecting data. Furthermore, the collection unit may also be equipped with a function to notify users of the purpose for which the data will be used after collection. This strengthens data privacy protection and gains user trust.

[0093] The analysis unit can also be equipped with a data visualization function when analyzing the operational data of the AI ​​system. For example, the analysis unit can display the collected data in graphs and charts, making it easier to visually understand trends and patterns in the data. The analysis unit can also evaluate the performance of the AI ​​system based on the data visualization results. Furthermore, the analysis unit can suggest areas for improvement to the AI ​​system based on the data visualization results. This makes it easier to intuitively understand the data analysis results.

[0094] The generation unit may also have an interactive explanation function when explaining the logic of the AI ​​system. For example, when a user inputs a question, the generation unit generates an answer to that question. The generation unit may also have a function that displays a detailed explanation of a specific part when the user clicks on that part. Furthermore, the generation unit may update the content of the explanation in real time based on user feedback. This makes it easier for users to understand the logic of the AI ​​system at their own pace.

[0095] When providing the generated explanation, the providing unit can select an explanation format according to the user's learning style. For example, the providing unit can provide an illustrated explanation to a user who prefers visual learning, and an audio explanation to a user who prefers auditory learning. The providing unit can also provide an interactive simulation to a user who prefers hands-on learning. Furthermore, the providing unit can adjust the difficulty of the explanation according to the user's learning progress. This can maximize the user's learning effect.

[0096] The analysis unit can estimate the user's emotions and adjust the presentation method of the analysis results based on the estimated user's emotions. For example, if the user is feeling stressed, the analysis unit can present a concise and to-the-point analysis result. Alternatively, if the user is relaxed, the analysis unit can present a detailed analysis result. Furthermore, if the user is in a hurry, the analysis unit can prioritize presenting the minimum necessary information in order to provide results quickly. In this way, by adjusting the presentation method of the analysis results according to the user's emotions, it is possible to provide information that is appropriate for the user.

[0097] The collection unit can estimate the user's emotions and adjust the frequency of data collection based on the estimated user emotions. For example, if the user is feeling stressed, the collection unit can reduce the frequency of data collection to reduce the burden on the user. Also, if the user is relaxed, the collection unit can increase the frequency of data collection to collect more detailed data. Furthermore, if the user is in a hurry, the collection unit can prioritize collecting the minimum amount of data necessary and complete collection quickly. In this way, adjusting the frequency of data collection according to the user's emotions can improve the quality of collected data.

[0098] The generation unit can estimate the user's emotions and adjust the tone of the generated explanation based on the estimated user's emotions. For example, if the user is feeling stressed, the generation unit can generate an explanation in a calm tone. If the user is relaxed, the generation unit can also generate an explanation in a friendly tone. Furthermore, if the user is in a hurry, the generation unit can also generate an explanation in a concise and direct tone. In this way, by adjusting the tone of the explanation according to the user's emotions, an explanation suitable for the user can be provided.

[0099] The providing unit can estimate the user's emotions and adjust the timing of the explanation to be provided based on the estimated user's emotions. For example, the providing unit temporarily refrains from providing an explanation when the user is feeling stressed. The providing unit can also provide a detailed explanation at an appropriate time when the user is relaxed. Furthermore, the providing unit can quickly provide the main points when the user is in a hurry. In this way, by adjusting the timing of providing the explanation according to the user's emotions, the explanation can be provided at a time that is appropriate for the user.

[0100] The analysis unit can estimate the user's emotions and adjust the analysis priority based on the estimated user's emotions. For example, if the user is feeling stressed, the analysis unit can prioritize the analysis of important data and postpone detailed analysis. The analysis unit can also prioritize the analysis of detailed data if the user is relaxed. Furthermore, if the user is in a hurry, the analysis unit can prioritize the analysis of the minimum amount of data necessary to provide results quickly. In this way, by adjusting the analysis priority according to the user's emotions, it is possible to provide analysis results that are suitable for the user.

[0101] The processing flow of the second embodiment will be briefly explained below.

[0102] Step 1: The collection unit collects operational data of the AI ​​system. For example, the collection unit records in detail what input the AI ​​system received, what processing it performed, and what output it generated. Specifically, in the case of image recognition, data such as the input image, processing details, and recognition results are collected. In the case of natural language processing, data such as the input text, processing details, and analysis results are collected. Furthermore, when a predictive model is used, data such as the input data, processing details, and prediction results are collected. Step 2: The analysis unit analyzes the data collected by the collection unit. Based on the collected data, the analysis unit analyzes the logic of the AI ​​system and identifies the algorithms and models used. Specifically, it analyzes the layer structure and weight distribution of the neural network, the algorithm flow and model structure, and resource usage during operation (e.g., CPU and memory usage). Step 3: The generator generates an explanation based on the logic analyzed by the analyzer. The generator uses text and diagrams to explain the role of each layer of the neural network, feature extraction, algorithm flow, model structure, and resource usage during operation. Step 4: The providing unit provides the explanation generated by the generating unit. The providing unit provides the explanation in a format selectable by the user (e.g., text format, diagram format, video format, etc.). The providing unit can also estimate the user's emotions and adjust the format and order of the explanation based on the estimated emotions.

[0103] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0104] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0105] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0106] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0107] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0108] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0109] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0110] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0111] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0112] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0113] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0114] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0115] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0116] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0117] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0118] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0119] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0120] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0121] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0122] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0123] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0124] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0125] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0126] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0127] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0128] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0129] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0130] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0131] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0132] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0133] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0134] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0135] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0136] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0137] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0138] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0139] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0140] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0141] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0142] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0143] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0144] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0145] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0146] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0147] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0148] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0149] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0150] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0151] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0152] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0153] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0154] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0155] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0156] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0157] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0158] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0159] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0160] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0161] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0162] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0163] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0164] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0165] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0166] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0167] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0168] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0169] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0170] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0171] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0172] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0173] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0174] [Explanation of symbols]

[0175] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A collection unit that collects operation data of the AI ​​system; an analysis unit that analyzes the data collected by the collection unit; a generation unit that generates an explanation based on the logic analyzed by the analysis unit; a providing unit that provides the explanation generated by the generating unit. A system characterized by:

2. The collecting unit It will record in detail what inputs the AI ​​system receives, what processing it performs, and what outputs it generates.

2. The system of claim 1.

3. The analysis unit Based on the collected data, we analyze the logic of the AI ​​system and identify what algorithms and models are being used.

2. The system of claim 1.

4. The generation unit Explains in text and diagrams the role of each layer of a neural network and the features it extracts.

2. The system of claim 1.

5. The providing unit Provide instructions in a user-selectable format 2. The system of claim 1.

6. The providing unit Provide explanations in text, diagrams, video, or other formats 2. The system of claim 1.

7. The collecting unit Inferring user sentiment and adjusting the type of data collected based on the estimated user sentiment 2. The system of claim 1.

8. The collecting unit At the time of collection, the operating environment of the AI ​​system is recorded in detail.

2. The system of claim 1.

Images